用流映射实现少步高效生成，3次求解即达顶尖效果
How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance
- 将生成引导建模为确定性最优控制，利用流映射统一现有方法
- 仅需3次数值积分步数（NFEs）就超越主流基线性能
- 无需训练、单轨迹运行，适合追求高速生成的开发者
在生成建模中，我们常希望生成最大化用户指定奖励（如美学质量或与人类偏好对齐）的样本，这一问题称为‘引导’。尽管广泛应用，现有方法要么需要昂贵的多粒子、多步方案，要么依赖难以理解的近似。本文将引导重新形式化为确定性最优控制问题，导出一个包含现有方法的算法层级。我们发现，近年来备受关注的‘流映射’自然出现在最优解中。基于此，提出无需训练、单轨迹的‘流映射奖励引导（FMRG）’框架，利用流映射同时完成积分与引导。在文本到图像任务上，FMRG以仅3次数值积分步数（NFEs）即达到或超过基线表现，相较之前最先进方法提速至少一个数量级。代码已公开于 https://github.com/jrrhuang/fmrg。
原文摘要 · Abstract (English)
In generative modeling, we often wish to produce samples that maximize a user-specified reward such as aesthetic quality or alignment with human preferences, a problem known as \textit{guidance}. Despite their widespread use, existing guidance methods either require expensive multi-particle, many-step schemes or rely on poorly understood approximations. We reformulate guidance as a \textit{deterministic optimal control problem}, yielding a hierarchy of algorithms that subsumes existing approaches at the coarsest level. We show that the \textit{flow map}, an object of significant recent interest for its role in fast inference, arises naturally in the optimal solution. Based on this observation, we propose \textbf{Flow Map Reward Guidance (FMRG)}: a training-free, \textit{single-trajectory} framework that uses the flow map to both integrate and guide the flow. At text-to-image scale, FMRG matches or surpasses baselines across inverse problems and reward-guided generation with \textbf{as few as 3 NFEs}, giving at least an order-of-magnitude speedup in comparison to prior state of the art. Code is available at https://github.com/jrrhuang/fmrg.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。